Refactor URLComponent to use WebBaseLoader instead of UnstructuredURLLoader

This commit is contained in:
Gabriel Luiz Freitas Almeida 2024-03-05 19:16:57 -03:00
commit b0d4a67863

View file

@ -1,6 +1,6 @@
from typing import Any, Dict, Optional from typing import Any, Dict
from langchain_community.document_loaders.url import UnstructuredURLLoader from langchain_community.document_loaders.web_base import WebBaseLoader
from langflow import CustomComponent from langflow import CustomComponent
from langflow.schema import Record from langflow.schema import Record
@ -8,7 +8,7 @@ from langflow.schema import Record
class URLComponent(CustomComponent): class URLComponent(CustomComponent):
display_name = "URL" display_name = "URL"
description = "Load a URL." description = "Load URLs and convert them to records."
def build_config(self) -> Dict[str, Any]: def build_config(self) -> Dict[str, Any]:
return { return {
@ -18,9 +18,9 @@ class URLComponent(CustomComponent):
async def build( async def build(
self, self,
urls: list[str], urls: list[str],
) -> Optional[Record]: ) -> Record:
loader = UnstructuredURLLoader(urls=urls) loader = WebBaseLoader(web_paths=urls)
docs = loader.load() docs = loader.load()
records = self.to_records(docs) records = self.to_records(docs)
return records return records